multimodal benchmark
GameWorld
GameWorld evaluates agents on interactive game environments, testing perception, planning, and sequential decision-making to accomplish in-game objectives.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
GameWorld Ranking
Higher score ranks better on this benchmark.
| 1 | BY | 31.2% | 100.0% | 2 | C | |
| 2 | BY | 25.9% | 0.0% | 2 | C |
GameWorld Score Distribution
A closer view of the leading scores on this benchmark.
GameWorld Highlights
The leading models and scores on this benchmark.
What is GameWorld?
What GameWorld measures and how its scores work.
GameWorld evaluates agents on interactive game environments, testing perception, planning, and sequential decision-making to accomplish in-game objectives.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- GameWorld
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- gameworld|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GameWorld.
Which model scores highest on GameWorld?
Seed 2.1 Pro is currently ranked first with 31.2%.
What does GameWorld measure?
GameWorld evaluates agents on interactive game environments, testing perception, planning, and sequential decision-making to accomplish in-game objectives.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.